Related papers: Entropy-Based Adaptive Weighting for Self-Training
Data augmentation methods have been shown to be a fundamental technique to improve generalization in tasks such as image, text and audio classification. Recently, automated augmentation methods have led to further improvements on image…
In contrast to SGD, adaptive gradient methods like Adam allow robust training of modern deep networks, especially large language models. However, the use of adaptivity not only comes at the cost of extra memory but also raises the…
Natural Language Processing (NLP) models risk overfitting to specific terms in the training data, thereby reducing their performance, fairness, and generalizability. E.g., neural hate speech detection models are strongly influenced by…
We study the process through which reasoning models trained with reinforcement learning on verifiable rewards (RLVR) can learn to solve new problems. We find that RLVR drives performance in two main ways: (1) by compressing pass@$k$ into…
Deep learning models suffer from catastrophic forgetting when trained in an incremental learning setting. In this work, we propose a novel approach to address the task incremental learning problem, which involves training a model on new…
Large reasoning models, such as OpenAI o1 and DeepSeek-R1, tend to become increasingly verbose as their reasoning capabilities improve. These inflated Chain-of-Thought (CoT) trajectories often exceed what the underlying problems require,…
Recent methodologies in LLM self-training mostly rely on LLM generating responses and filtering those with correct output answers as training data. This approach often yields a low-quality fine-tuning training set (e.g., incorrect plans or…
Self-improvement training enables the large reasoning models (LRMs) to improve themselves by self-generating reasoning trajectories as training data without external supervision. However, we find that this method often falls short in…
Large Reasoning Models (LRMs) often suffer from overthinking, generating unnecessarily long reasoning chains even for simple tasks. This leads to substantial computational overhead with limited performance gain, primarily due to redundant…
Supervised fine-tuning enhances the problem-solving abilities of language models across various mathematical reasoning tasks. To maximize such benefits, existing research focuses on broadening the training set with various data augmentation…
Self-training has become a popular semi-supervised learning technique for leveraging unlabeled data. However, the over-confidence of pseudo-labels remains a key challenge. In this paper, we propose a novel \emph{graph-based…
While recent self-training approaches have reduced reliance on human-labeled data for aligning LLMs, they still face critical limitations: (i) sensitivity to synthetic data quality, leading to instability and bias amplification in iterative…
Transformers empirically perform precise probabilistic reasoning in carefully constructed ``Bayesian wind tunnels'' and in large-scale language models, yet the mechanisms by which gradient-based learning creates the required internal…
Large pre-trained vision-language models (VLMs), such as CLIP, demonstrate impressive generalization but remain highly vulnerable to adversarial examples (AEs). Previous work has explored robust text prompts through adversarial training,…
The newly released OpenAI-o1 and DeepSeek-R1 have demonstrated that test-time scaling can significantly improve model performance, especially in complex tasks such as logical reasoning. Common test-time scaling methods involve generating…
Despite the fact that adversarial training has become the de facto method for improving the robustness of deep neural networks, it is well-known that vanilla adversarial training suffers from daunting robust overfitting, resulting in…
Stochasticity in language model fine-tuning, often caused by the small batch sizes typically used in this regime, can destabilize training by introducing large oscillations in generation quality. A popular approach to mitigating this…
Mixed precision training (MPT) is becoming a practical technique to improve the speed and energy efficiency of training deep neural networks by leveraging the fast hardware support for IEEE half-precision floating point that is available in…
Reasoning models often outperform smaller models but at 3--5$\times$ higher cost and added latency. We present entropy-guided refinement: a lightweight, test-time loop that uses token-level uncertainty to trigger a single, targeted…
Large language models are typically post-trained using supervised fine-tuning (SFT) and reinforcement learning (RL), yet effectively unifying efficient knowledge injection with robust generalization remains challenging. In this work, we…